What solutions does Rostelecom have for IIoT?
Hello!
Recently, together with Geekbrains, we conducted a hackathon dedicated to the industrial Internet of Things IIoT and now we are starting to spread a series of interviews with our experts. The first of them is a conversation with Nikolay Chevalier, the chief architect of the project office Industrial of the Internet of Things of Rostelecom.
')
Nikolay will tell you what industrial Internet of things is and how it differs from the usual IoT, as well as about the solutions that Rostelecom already has.
Under the cut - about the role of IIoT in the automation of housing and utilities, agriculture, smart offices and much more.
Nicholas Chevalier: this slide is a reflection of all the technological aspects that may somehow be present in industrial Internet projects. As you can see from the picture, there are a lot of aspects, so I will briefly tell about each of them.
In a general sense, the industrial Internet is a new round of automation, allowing to achieve a higher quality level in various industries. Here we are talking about agriculture, and nuclear energy, and metallurgy. In fact, this is a subsection of the Internet of things, but it is focused on industrial solutions. The structure of the picture should be viewed from the bottom up - from sensors to information systems.
Sensors and devices collect information from both physical and cyber-physical systems, and this allows us to work with such data. Here we have all sorts of sensors, robots, video analytics, security systems (both the usual security and labor safety).
A level above - Edge , these are systems that are in production near the devices. Directly on the factories in the contours of technical processes. Process control system (automatic process control system), fire alarm and similar systems that require a minimum delay from the occurrence of some event to the reaction to it.
Even higher is the Data Transmission Network , the task of which is to transfer this data to computer centers for further processing. Radio networks, overlay networks, fixed networks. By the way, what's the difference: fixed networks are optical lines, carrying the backbone of the entire communication system in general. There will not be them, there will be no radio communication, because radio communication without optics will not work. This last mile radio allows you to efficiently and quickly connect devices without pulling the cable. But before this last mile cable is required. Superimposed networks are routing and traffic management systems, with their help, you can organize dedicated private networks on top of any structure with the necessary level of protection.
After networks - the infrastructure of data centers (where storage, server, IDS, firewalls) and software for working with information (virtualization).
At the same level, the classic set - the data centers themselves, data storage, backup services, IaaS, and the like ...
Separately, I note software that allows you to organize work with data , as well as their processing and storage. Here, the trend in terms of computing in memory, the blockchain is very actively gaining momentum (in one of the utopian options for the development of technology, various IIoT solutions will be able to interact with each other as part of smart contacts).
The next global level is smarter systems . Artificial intelligence, various billing systems, production management systems, security monitoring, collecting data from all security levels using AI and analytics systems.
In general, this is briefly to describe the scheme of the organization IIoT. The important thing is: special information security systems are applied at every level. And a solution can be considered as protected only when all its levels are protected and all organizational processes of employees that interact with such a solution are taken into account.
This slide is about LP WAN. These are energy efficient long-haul networks. The most famous and well-established standards are LORA-WAN, SigFox, LTE-Cat NB (NB-ioT), LTE-CAT M1. To understand the level of action of such networks, it is easier to compare them with household ones. Here we have all Bluetooth - this is a stable job and communication with devices in a radius from a couple of meters to a couple of tens of meters. Then come the cellular networks - 2G, 3G, 4G. And behind them - LP WAN, the network of the long-range, they have the largest coverage radius and they allow to achieve a certain level of energy efficiency. For example, there is a gas meter that transmits readings once at a given time, and you can use it for 10 years without changing the battery.
Here is a slide from our colleagues involved in information security, which shows common threats.
Of course, if the service works only for a couple of IP, you can simply close the loop, and by this, ensure the necessary level of protection. But if this is an open service, which implies the interaction of users with it, then the usual network threats can be superimposed here. Spam bots, hacker attacks, DDoS and other good. To protect against this, a large number of technical means of protection are used that in case of emergency situations are alerted to the security operation centers - there are specially trained security personnel sitting there and reacting to specified events.
For utilities, there is a special service developed in Rostelecom, which allows you to automate the acquisition of data from metering devices that almost everyone has in the apartment: water meters, electricity, and both individual and general-purpose meters. If earlier these values ​​had to be entered manually, which leads to a waste of time and to the transfer of not quite correct readings, now in the Russian Federation there are already a number of complexes where human participation in this process is completely excluded. All these things are successfully automated, and they themselves collect evidence from all sensors and transfer them to management and resource supply companies.
In addition to utilities in general, we have developed an integrated special solution for electricity metering. The terrible abbreviation of AMR on the slide is just an Automated System for Commercial Accounting for Electric Power. What she does is clear from the title. These are counters that are installed at the substations themselves, at user connection points, at generation — all this allows power engineers to understand how efficiently the services work. The scheme of work is simple: metering device - link of communication channel - Data Centers - an application that visualizes and processes data.
The smart office solution helps to fix a number of indicators that are important for comfortable work of a person in an office environment. First of all, these are CO2 levels and light levels, which are often underestimated, as well as the total consumption of electricity. There are two “hares on the sights” at once: it is more comfortable for the employees to work, and for the operating personnel it helps to save by more rational use of resources.
In addition to offices, there are more hazardous industries where it is necessary to reduce possible injuries and monitor personnel. The main idea here - to know that the employee is all right with well-being, and that he is where it is necessary, and is not where it is not necessary. For plants with a large number of moving mechanisms, this is critical. There are many different sensors, from gas analyzers to bracelets that monitor both the pulse and the status of an employee, and his location. This helps to notify the system in time that an employee has suddenly found himself where he is now dangerous to be (for example, a crane is moving or a gas release is planned). In this case, the system will suspend work, automatically notify the person in charge and wait until the person leaves the danger zone. And then there are smart helmets, which record the presence of a blow or acid on their surface, and immediately notify personnel responsible for industrial safety.
Agriculture had the task of controlling the control of crop movement. This means that it was necessary to understand when the combine is unloaded, when the transportation module is loaded. Here it is important to note in advance that the modern combine is very different from the one on which the wolf rode in “Well, wait a minute” - today it is a serious machine equipped with an on-board computer, telling the main system its state and telemetry. This is already a reality; there are such combines in the Russian Federation, including unmanned models.
Of course, what we are doing now is aimed precisely at the current fleet of cars - they are not unmanned, but still quite “smart”, we automate the process of selecting the devices themselves and create a control system for working with devices.
In Rostelecom, together with other companies, we have implemented monitoring of cattle. The task of agriculture here was this - there is a need to understand when the cows are ready to breed, are ill or not, exactly where they are grazing. This is all important in order to determine the best moments - to understand whether a cow is ready to mate, or has a headache, whether it is time to let out bulls or wait, to react in time to an animal's illness and so on. Such decisions help and monitor the condition of animals, and improve product quality, and monitor profitability.
It is not enough just to collect and store data - you need to work with them. This helps predictive analytics scenarios. For example, we collected data, while we know where and when this data was collected, add to this volume the design research institutes calculations, information on production events, including non-nominal ones, add basic information about industry processes, whether it is energy or agriculture . We normalize this data with the help of mathematics and models. And then we add analytics and a predictive component.
Predictive analytics module looks like this:
This is the construction of predictive models. There is a contour in which data is modeled, and systems in which they are recorded. In addition, test data sets, training data sets and, of course, real data. This is an ongoing process, the model must be further trained. Now a good indicator for the model is 90% accuracy. The average value is still in most models - 85-87.
Do you want to replace existing SCADA with IIoT?
Good question. In fact, the existing SCADA - they are very different. If we consider the very concept of IIoT, SCADA is suitable for it, as well as MES-systems, they can also stand within the framework of IIoT. This does not mean that they need to be changed, there are several options.
The IIoT platform is connected to the MES system or SCADA already ready.
When there is a high-quality replacement of equipment that does not need SCADA, because it can do all these things quickly at its own level.
There is an Edge-level, where SCADA is framed in a certain fog-variant.
That is, SCADA will be replaced with SCADA in the unfolded fog, it will be a new platform Edge-level, managed centrally, but located on a local point. And in this infrastructure, the solution will be deployed in fact the same SCADA, but in a different control loop.
Therefore, as a class SCADA will not go anywhere, just transformed.
What are the main tasks now facing the IIoT Rostelecom?
Now it has 4 sectors - agriculture, manufacturing, fuel and energy and energy. The digitization of each industry seems very promising.
Interesting systems of control of people in enterprises - whether they work, how well, whether the regulations violate. Such cases are very often solved by video analytics or control of machine tools that people work for, that's how the plant from which we took datas for tasks. With this approach, the plant doubled its productivity, simply because they began to watch: the machine is idle = they do not use it. And the point here is not that the employees worked so-so; there the processes themselves were just like that, that sometimes there were downtime.
Nowadays, Kaizen production systems or lean manufacturing are relevant; within the system, a manager needs data to make decisions. We need data collection from metering devices, we need their visualization. It is not by chance that I so often speak about visualization, it is important because it helps to look at the same data set from different angles.
We received 434 applications for the call to get together and write an IIoT solution for real business, and as a result, 184 people participated in 35 teams. These are novice developers who have tried their hand at a new area.
Of them reached the finish line and presented their projects to 33 teams, 174 participants. We see the best of them at Rostelecom. That's how it was.
The video version of the interview is here .
Recently, together with Geekbrains, we conducted a hackathon dedicated to the industrial Internet of Things IIoT and now we are starting to spread a series of interviews with our experts. The first of them is a conversation with Nikolay Chevalier, the chief architect of the project office Industrial of the Internet of Things of Rostelecom.
')
Nikolay will tell you what industrial Internet of things is and how it differs from the usual IoT, as well as about the solutions that Rostelecom already has.
Under the cut - about the role of IIoT in the automation of housing and utilities, agriculture, smart offices and much more.
Nicholas Chevalier: this slide is a reflection of all the technological aspects that may somehow be present in industrial Internet projects. As you can see from the picture, there are a lot of aspects, so I will briefly tell about each of them.
Industrial internet
In a general sense, the industrial Internet is a new round of automation, allowing to achieve a higher quality level in various industries. Here we are talking about agriculture, and nuclear energy, and metallurgy. In fact, this is a subsection of the Internet of things, but it is focused on industrial solutions. The structure of the picture should be viewed from the bottom up - from sensors to information systems.
Sensors and devices collect information from both physical and cyber-physical systems, and this allows us to work with such data. Here we have all sorts of sensors, robots, video analytics, security systems (both the usual security and labor safety).
A level above - Edge , these are systems that are in production near the devices. Directly on the factories in the contours of technical processes. Process control system (automatic process control system), fire alarm and similar systems that require a minimum delay from the occurrence of some event to the reaction to it.
Even higher is the Data Transmission Network , the task of which is to transfer this data to computer centers for further processing. Radio networks, overlay networks, fixed networks. By the way, what's the difference: fixed networks are optical lines, carrying the backbone of the entire communication system in general. There will not be them, there will be no radio communication, because radio communication without optics will not work. This last mile radio allows you to efficiently and quickly connect devices without pulling the cable. But before this last mile cable is required. Superimposed networks are routing and traffic management systems, with their help, you can organize dedicated private networks on top of any structure with the necessary level of protection.
After networks - the infrastructure of data centers (where storage, server, IDS, firewalls) and software for working with information (virtualization).
At the same level, the classic set - the data centers themselves, data storage, backup services, IaaS, and the like ...
Separately, I note software that allows you to organize work with data , as well as their processing and storage. Here, the trend in terms of computing in memory, the blockchain is very actively gaining momentum (in one of the utopian options for the development of technology, various IIoT solutions will be able to interact with each other as part of smart contacts).
The next global level is smarter systems . Artificial intelligence, various billing systems, production management systems, security monitoring, collecting data from all security levels using AI and analytics systems.
In general, this is briefly to describe the scheme of the organization IIoT. The important thing is: special information security systems are applied at every level. And a solution can be considered as protected only when all its levels are protected and all organizational processes of employees that interact with such a solution are taken into account.
More details
Network
This slide is about LP WAN. These are energy efficient long-haul networks. The most famous and well-established standards are LORA-WAN, SigFox, LTE-Cat NB (NB-ioT), LTE-CAT M1. To understand the level of action of such networks, it is easier to compare them with household ones. Here we have all Bluetooth - this is a stable job and communication with devices in a radius from a couple of meters to a couple of tens of meters. Then come the cellular networks - 2G, 3G, 4G. And behind them - LP WAN, the network of the long-range, they have the largest coverage radius and they allow to achieve a certain level of energy efficiency. For example, there is a gas meter that transmits readings once at a given time, and you can use it for 10 years without changing the battery.
Data Center Protection
Here is a slide from our colleagues involved in information security, which shows common threats.
Of course, if the service works only for a couple of IP, you can simply close the loop, and by this, ensure the necessary level of protection. But if this is an open service, which implies the interaction of users with it, then the usual network threats can be superimposed here. Spam bots, hacker attacks, DDoS and other good. To protect against this, a large number of technical means of protection are used that in case of emergency situations are alerted to the security operation centers - there are specially trained security personnel sitting there and reacting to specified events.
Housing and communal services
For utilities, there is a special service developed in Rostelecom, which allows you to automate the acquisition of data from metering devices that almost everyone has in the apartment: water meters, electricity, and both individual and general-purpose meters. If earlier these values ​​had to be entered manually, which leads to a waste of time and to the transfer of not quite correct readings, now in the Russian Federation there are already a number of complexes where human participation in this process is completely excluded. All these things are successfully automated, and they themselves collect evidence from all sensors and transfer them to management and resource supply companies.
Power industry
In addition to utilities in general, we have developed an integrated special solution for electricity metering. The terrible abbreviation of AMR on the slide is just an Automated System for Commercial Accounting for Electric Power. What she does is clear from the title. These are counters that are installed at the substations themselves, at user connection points, at generation — all this allows power engineers to understand how efficiently the services work. The scheme of work is simple: metering device - link of communication channel - Data Centers - an application that visualizes and processes data.
Smart office
The smart office solution helps to fix a number of indicators that are important for comfortable work of a person in an office environment. First of all, these are CO2 levels and light levels, which are often underestimated, as well as the total consumption of electricity. There are two “hares on the sights” at once: it is more comfortable for the employees to work, and for the operating personnel it helps to save by more rational use of resources.
Monitoring of production personnel
In addition to offices, there are more hazardous industries where it is necessary to reduce possible injuries and monitor personnel. The main idea here - to know that the employee is all right with well-being, and that he is where it is necessary, and is not where it is not necessary. For plants with a large number of moving mechanisms, this is critical. There are many different sensors, from gas analyzers to bracelets that monitor both the pulse and the status of an employee, and his location. This helps to notify the system in time that an employee has suddenly found himself where he is now dangerous to be (for example, a crane is moving or a gas release is planned). In this case, the system will suspend work, automatically notify the person in charge and wait until the person leaves the danger zone. And then there are smart helmets, which record the presence of a blow or acid on their surface, and immediately notify personnel responsible for industrial safety.
Agriculture
Agriculture had the task of controlling the control of crop movement. This means that it was necessary to understand when the combine is unloaded, when the transportation module is loaded. Here it is important to note in advance that the modern combine is very different from the one on which the wolf rode in “Well, wait a minute” - today it is a serious machine equipped with an on-board computer, telling the main system its state and telemetry. This is already a reality; there are such combines in the Russian Federation, including unmanned models.
Of course, what we are doing now is aimed precisely at the current fleet of cars - they are not unmanned, but still quite “smart”, we automate the process of selecting the devices themselves and create a control system for working with devices.
Cattle Monitoring
In Rostelecom, together with other companies, we have implemented monitoring of cattle. The task of agriculture here was this - there is a need to understand when the cows are ready to breed, are ill or not, exactly where they are grazing. This is all important in order to determine the best moments - to understand whether a cow is ready to mate, or has a headache, whether it is time to let out bulls or wait, to react in time to an animal's illness and so on. Such decisions help and monitor the condition of animals, and improve product quality, and monitor profitability.
Why is there artificial intelligence
It is not enough just to collect and store data - you need to work with them. This helps predictive analytics scenarios. For example, we collected data, while we know where and when this data was collected, add to this volume the design research institutes calculations, information on production events, including non-nominal ones, add basic information about industry processes, whether it is energy or agriculture . We normalize this data with the help of mathematics and models. And then we add analytics and a predictive component.
Predictive analytics module looks like this:
This is the construction of predictive models. There is a contour in which data is modeled, and systems in which they are recorded. In addition, test data sets, training data sets and, of course, real data. This is an ongoing process, the model must be further trained. Now a good indicator for the model is 90% accuracy. The average value is still in most models - 85-87.
In preparation for the hackathon, participants received questions on the topic.
Do you want to replace existing SCADA with IIoT?
Good question. In fact, the existing SCADA - they are very different. If we consider the very concept of IIoT, SCADA is suitable for it, as well as MES-systems, they can also stand within the framework of IIoT. This does not mean that they need to be changed, there are several options.
The IIoT platform is connected to the MES system or SCADA already ready.
When there is a high-quality replacement of equipment that does not need SCADA, because it can do all these things quickly at its own level.
There is an Edge-level, where SCADA is framed in a certain fog-variant.
That is, SCADA will be replaced with SCADA in the unfolded fog, it will be a new platform Edge-level, managed centrally, but located on a local point. And in this infrastructure, the solution will be deployed in fact the same SCADA, but in a different control loop.
Therefore, as a class SCADA will not go anywhere, just transformed.
What are the main tasks now facing the IIoT Rostelecom?
Now it has 4 sectors - agriculture, manufacturing, fuel and energy and energy. The digitization of each industry seems very promising.
Interesting systems of control of people in enterprises - whether they work, how well, whether the regulations violate. Such cases are very often solved by video analytics or control of machine tools that people work for, that's how the plant from which we took datas for tasks. With this approach, the plant doubled its productivity, simply because they began to watch: the machine is idle = they do not use it. And the point here is not that the employees worked so-so; there the processes themselves were just like that, that sometimes there were downtime.
Nowadays, Kaizen production systems or lean manufacturing are relevant; within the system, a manager needs data to make decisions. We need data collection from metering devices, we need their visualization. It is not by chance that I so often speak about visualization, it is important because it helps to look at the same data set from different angles.
About hackathon
We received 434 applications for the call to get together and write an IIoT solution for real business, and as a result, 184 people participated in 35 teams. These are novice developers who have tried their hand at a new area.
Of them reached the finish line and presented their projects to 33 teams, 174 participants. We see the best of them at Rostelecom. That's how it was.
The video version of the interview is here .
Source: https://habr.com/ru/post/452152/
All Articles